{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-to-fuse-things-and-stuff","title":"Learning to Fuse Things and Stuff","arxiv_id":"1812.01192","date":"2018-12-04","proceeding":null,"authors":["Jie Li","Allan Raventos","Arjun Bhargava","Takaaki Tagawa","Adrien Gaidon"],"abstract":"We propose an end-to-end learning approach for panoptic segmentation, a novel task unifying instance (things) and semantic (stuff) segmentation. Our model, TASCNet, uses feature maps from a shared backbone network to predict in a single feed-forward pass both things and stuff segmentations. We explicitly constrain these two output distributions through a global things and stuff binary mask to enforce cross-task consistency. Our proposed unified network is competitive with the state of the art on several benchmarks for panoptic segmentation as well as on the individual semantic and instance segmentation tasks.","url_abs":"https://arxiv.org/abs/1812.01192v2","url_pdf":"https://arxiv.org/pdf/1812.01192v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/panoptic-segmentation-on-coco-test-dev","task":"Panoptic Segmentation","dataset":"COCO test-dev","model":"TASCNet","rank_in_archive_order":33,"of":38,"metrics":{"PQ":"40.7","PQst":"31.0","PQth":"47.0"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-cityscapes-val","task":"Panoptic Segmentation","dataset":"Cityscapes val","model":"TASCNet (ResNet-50, multi-scale)","rank_in_archive_order":27,"of":37,"metrics":{"AP":"39","PQ":"60.4","PQst":"63.3","PQth":"56.1","mIoU":"78"},"uses_additional_data":true},{"leaderboard":"/sota/panoptic-segmentation-on-cityscapes-val","task":"Panoptic Segmentation","dataset":"Cityscapes val","model":"TASCNet (ResNet-50)","rank_in_archive_order":29,"of":37,"metrics":{"AP":"37.6","PQ":"59.2","PQst":"61.5","PQth":"56","mIoU":"77.8"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1812.01192","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}